Joint Extraction of Cerebrum and Cerebellum from Lifespan MRIs

Motivation: Most existing neuroimaging pipelines struggle to accurately extract cerebrum and cerebellum from lifespan MRI images, negatively impacting neurological diagnostics and treatment. Goal(s): We propose a joint extraction method for the cerebrum and cerebellum from lifespan MR images to improve analysis across diverse age groups and imaging protocols. Approach: Our method integrates intracranial segmentation for tissue isolation, uses deformable registration for anatomical alignment, and applies labeling to produce a joint mask for cerebrum and cerebellum. Results: Evaluating our method on 30,000+ lifespan images demonstrated significant improvements over state-of-the-art methods and robust performance across multi-modality images. Impact: Our method unifies cerebrum and cerebellum extraction, addressing anatomical differences, reducing time complexity, and ensuring accuracy across modalities and ages. This enhances neurological research and clinical diagnostics by enabling precise analysis and monitoring of brain structures.